Ural Federal University (Ekaterinburg, Russia):

P. F. Chernavin, Cand. Econ., Associate Professor, Dept. of Big Data Analytics and Video Analysis Methods, e-mail: chernavin.p.f@gmail.com
A. V. Malygin, Dr. Eng., Professor, Dept. of Metallurgy of Iron and Alloys, Deputy Director of Ferrox Ltd., e-mail: a.malygin@urfu.ru

Severstal (Cherepovets, Russia):
T. V. Detkova, Head of the Center for Raw Materials Research, e-mail: tvdetkova@severstal.com
V. Yu. Kuchin, Leading Expert, e-mail: vyukuchin@severstal.com

Abstract: This article proposes a method for a comprehensive analysis of the controlled parameters of the technological process and the dynamics of sinter cake disintegration during mechanical processing, taking into account the transport lag of the measured output characteristics (fines yield 0-5 mm when sinter cake is destroyed within the sinter plant and along the conveyor path for transporting sinter to the blast furnace shop) from the current composition of the charge and the parameters of the sintering process. On the basis of the specified output characteristics, an assessment of the sinter yield and strength was carried out. To analyze and predict the physical and mechanical properties of iron ore sinter, a new method of constructing regression equations based on linear programming problems with partially Boolean variables was used. The most significant drawback of the standard approach is the strong dependence of the regression equation coefficients on random anomalous observations (outliers), which in practical problems can be quite large and it is impossible to filter them out. The proposed MILP Regression method improves the forecast quality by automatically excluding atypical observations from consideration. The method is compared with other regression models. The method of mixed integer linear programming (MLIP) was used to process the current information about the operation of the sinter shop No. 3. The most significant parameters that affect the formation of the total amount of fines during the destruction of sinter were established: the component composition of the charge, sinter machine pallets speed, pressure gas and temperature in collectors, temperature in ignition furnaces and behind them, temperature in last vacuum chambers of sintering machines. The obtained regression equations quite accurately reflect the influence of the initial data array on the yield of recycled sintering products and they can be used to predict the output parameters of the sinter quality.

A. A. Eliseev, manager on raw materials research (PJSC Severstal), Yu. A. Malygin, director (JSC Ferroks), N. P. Chernavin, assistant of the department “Big data analytics and video analysis methods” (Ural federal university), F. P. Chernavin, associate professor, department “Simulation of managing systems” (Ural federal university) participated in preparation of this article.

1. Frolov Yu. А. Agglomeration. Technology, heating engineering, management, ecology. Moscow: Metallurgizdat, 2016. 672 p.
2. Frolov Yu. А., Filatov S. V., Kaplun L. I., Semenov О. А. Influence of the component composition and charge layer height on the quality of sinter, fuel consumption and productivity of sintering machines of PJSC NLMK. Metallurg. 2020. No. 4. pp. 21–29.
3. Mansurova N. R. Influence of the genesis and basicity of the charge on the mineralogical composition and metallurgical properties of the sinter: thesis of inauguration of Dissertation … of Candidate of Engineering Sciences. Moscow: Moscow State Steel Institute, 2007. 26 p.
4. Nechkin G. А., Chernavin D. А., Isaenko G. Е. Optimization of blast-furnace charge by a set of metallurgical properties. Chernaya metallurgiya. Byulleten nauchno-tekhnicheskoy i ekonomicheskoy informatsii. 2019. Vol. 75. No. 11. pp. 1244–1250.
5. Demidova N. V. Influence of the agglomeration process parameters on the agglomerate quality. Nauka i proizvodstvo Urala. 2016. No. 12. pp. 2–5.
6. Shapovalov А. N., Ovchinnikova Е. V. et. al. Improvement of the quality of sintering charge preparation for sintering in the conditions of JSC Ural Steel. Metallurg. 2015. No. 3. pp. 30–36.
7. Malygin А. V., Shumakov N. S. The dynamics of the sinter cake disintegration during machining. Izvestiya vuzov. Chernaya metallurgiya. 1997. No. 9. pp. 9–12.
8. Johnson N. S., Vulimiri P. S., To A. C., Brice C. A. Invited review: machine learning for materials developments in metals additive manufacturing. Additive Manufacturing. 2020. Vol. 36. pp. 1–30.
9. Zhang B., Zi J., Li M. Prediction of sinter yield and strength in iron sintering process by numerical simulation. Applied Thermal Engineering. 2018. Vol. 131. pp. 70–79.
10. Webster N., Pownceby M., Ware N., Pattel R. Predicting iron ore sinter strength through partial least square regression (PLSR) analysis of X-ray diffraction patterns. Powder diffraction. 2017. Vol. 32. pp. 66–69.
11. Jian-Liang Zh. Effects of MgO on the sintering liquid, the properties and mineralogical morphology of the high-basity sinter. 7 European Coke and Ironmaking Congress. 2016. pp. 122.
12. Kumar V., Sairam D., Kumar S., Singh A. et al. Prediction of iron ore sinter properties using statistical technique. Transaction of the Indian Institute of Metals. 2016. Vol. 70. Iss. 6. pp. 1661–1670.
13. Wang Y., Zhang J., Zhang Y., Liu D., Liu Y. Characteristics of combustion zone and evolution of mineral phases along bed height in ore sintering. International Journal of Minerals, Metallurgy and Materials. 2017. Vol. 24. pp. 1087–1095.
14. Chernavin P. F., Chernavin F. P. Chernavin N. P. Reduction of regression problems to linear integer programming problems. Analysis, modeling, management, development of socioeconomic systems: collection of scientific works of the XIV All-Russian school-symposium with international participation. 2020. pp. 383–386.